Semantic Structuring of Shapes and Other Visual Data

Mewes, Daniel

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Thesis

Semantic Structuring of Shapes and Other Visual Data

MPS-Authors

/persons/resource/persons45034

Mewes, Daniel
Computer Graphics, MPI for Informatics, Max Planck Society;

External Resource

No external resources are shared

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Mewes, D. (2013). Semantic Structuring of Shapes and Other Visual Data. Master Thesis, Universität des Saarlandes, Saarbrücken.

Cite as: https://hdl.handle.net/11858/00-001M-0000-0015-3E06-3

Abstract

Crowd-sourced data bases such as Flickr for images or Google 3D Warehouse for 3D meshes provide vast amounts of shape data. While the shapes in these databases come annotated with user-provided semantic labels, those annotations are noisy and inconsistent. Organizing these data sets by semantic criteria therefore remains a difficult task. We explore techniques that use machine learning for finding out how images and 3D meshes can be associated with the corresponding semantic labels. We present how an existing method for large-scale image annotation ("WSABIE" by Weston et al. 2011) can be extended to support a multi modal setting, in which we can learn a joint semantic structuring of both meshes and images.